how to my trading strategy evaluation in machine learning?
If you are using supervised learning techniques, you can always check the performance of an ML model using metrics such as accuracy, precision, recall, or the confusion matrix for example. This is a way to quantify the performance of an ML Model, which can be used to compare different ML models as well.
The beauty of backtesting is that you can always backtest the ML model on historical data and use metrics such as winning trades, losing trades, win-loss ratio, p/l per trade, overall profit. This will help you understand the performance in detail and help you move ahead when you are satisfied with the performance.
Hope this helps.
Thanks …